Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Fixed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     timetable
    -0.08
    urut
    -0.08
    geometry
    -0.08
     пользу
    -0.07
     الخار
    -0.07
     incorpor
    -0.07
     достаточно
    -0.07
     probabilities
    -0.07
    的邀请码
    -0.07
     extr
    -0.07
    POSITIVE LOGITS
     moth
    0.08
    ameda
    0.08
    สาว
    0.08
     seafood
    0.08
     fish
    0.07
     lagu
    0.07
     beet
    0.07
    _POLICY
    0.07
    TOP
    0.07
    ritter
    0.07
    Act Density 0.001%

    No Known Activations